noahjgreer
commented
10 months ago Yes! I am also receiving this same error. I have tried reinstalling kohya_ss, tried updating/reinstalling the scipy package, but both have not solved the problem. I also have checked twice, and the bitsandbytes package is installed. Not sure what's going on. I am running Windows.
Microsoft Windows [Version 10.0.20348.2031]
(c) Microsoft Corporation. All rights reserved.
F:\StableDiffusionProjects\kohya_ss>gui.bat
←[1;33m=============================================================
Modules installed outside the virtual environment were found.
This can cause issues. Please review the installed modules.
You can uninstall all local modules with:
←[1;34mdeactivate
pip freeze > uninstall.txt
pip uninstall -y -r uninstall.txt
←[1;33m=============================================================←[0m
11:09:20-452466 INFO Version: v22.1.1
11:09:20-460473 INFO nVidia toolkit detected
11:09:22-381283 INFO Torch 2.0.1+cu118
11:09:22-407306 INFO Torch backend: nVidia CUDA 11.8 cuDNN 8700
11:09:22-410308 INFO Torch detected GPU: NVIDIA GeForce RTX 2060 SUPER VRAM 8192 Arch (7, 5) Cores 34
11:09:22-411309 INFO Verifying modules installation status from requirements_windows_torch2.txt...
11:09:22-414312 INFO Verifying modules installation status from requirements.txt...
11:09:25-379018 INFO headless: False
11:09:25-383022 INFO Load CSS...
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
11:10:00-604283 INFO Loading config...
11:10:01-791092 INFO Loading config...
11:10:06-471806 INFO Start training LoRA Standard ...
11:10:06-472806 INFO Checking for duplicate image filenames in training data directory...
11:10:06-474808 INFO Valid image folder names found in: F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/img11:10:06-477811 INFO Valid image folder names found in: F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/reg11:10:06-479814 INFO Folder 25_f1nni fox: 7 images found
11:10:06-481815 INFO Folder 25_f1nni fox: 175 steps
11:10:06-483817 WARNING Regularisation images are used... Will double the number of steps required...
11:10:06-484818 INFO Total steps: 175
11:10:06-485819 INFO Train batch size: 1
11:10:06-486820 INFO Gradient accumulation steps: 1
11:10:06-488822 INFO Epoch: 12
11:10:06-491825 INFO Regulatization factor: 2
11:10:06-497830 INFO max_train_steps (175 / 1 / 1 * 12 * 2) = 4200
11:10:06-502836 INFO stop_text_encoder_training = 0
11:10:06-507839 INFO lr_warmup_steps = 0
11:10:06-509842 INFO Saving training config to
F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/model\lora_Finni-v1.1-NoAI_SD15_202311 13-111006.json...
11:10:06-514846 INFO accelerate launch --num_cpu_threads_per_process=2 "./train_network.py" --enable_bucket
--min_bucket_reso=256 --max_bucket_reso=2048
--pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5"
--train_data_dir="F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/img"
--reg_data_dir="F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/reg"
--resolution="512,512"
--output_dir="F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/model"
--logging_dir="F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/log"
--network_alpha="1" --save_model_as=safetensors --network_module=networks.lora --network_dim=8
--output_name="lora_Finni-v1.1-NoAI_SD15" --lr_scheduler_num_cycles="12" --no_half_vae
--learning_rate="0.0001" --lr_scheduler="constant" --train_batch_size="1"
--max_train_steps="4200" --save_every_n_epochs="1" --mixed_precision="fp16"
--save_precision="fp16" --seed="58008" --cache_latents --optimizer_type="AdamW8bit"
--max_token_length=150 --clip_skip=2 --bucket_reso_steps=64 --shuffle_caption --xformers
--bucket_no_upscale --noise_offset=0.0
prepare tokenizer
update token length: 150
Using DreamBooth method.
prepare images.
found directory F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox contains 7 image files
No caption file found for 7 images. Training will continue without captions for these images. If class token exists, it will be used. / 7枚の画像にキャプションファイルが見つかりませんでした。これらの画像についてはキャプションなしで学習を続行します。class tokenが存在する場合はそれを使います。
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00000-0-image-000.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00001-0-image-001.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00002-0-image-002.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00003-0-image-003.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00004-0-image-004.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox\00005-0-image-005.png... and 2 more
found directory F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox contains 200 image files
No caption file found for 200 images. Training will continue without captions for these images. If class token exists, it will be used. / 200枚の画像にキャプションファイルが見つかりませんでした。これらの画像についてはキャプションなしで学習を続行します。class tokenが存在する場合はそれを使います。
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d05351a88695810ce59ddca92080cd37.jpg
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d131cb2277d8e370ab5a04183ded0bb6.jpg
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d14dfc8b13ed925db973047c3828de90.jpg
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d15ac65a8720ebc664039d2681266782.png
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d15ba6e15ff454ba64b3d51af21e5de8.jpg
F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox\d16ec70b2151c66fa5c87162937cda93.png... and 195 more
175 train images with repeating.
200 reg images.
some of reg images are not used / 正則化画像の数が多いので、一部使用されない正則化画像があります
[Dataset 0]
batch_size: 1
resolution: (512, 512)
enable_bucket: True
min_bucket_reso: 256
max_bucket_reso: 2048
bucket_reso_steps: 64
bucket_no_upscale: True
[Subset 0 of Dataset 0]
image_dir: "F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\img\25_f1nni fox"
image_count: 7
num_repeats: 25
shuffle_caption: True
keep_tokens: 0
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
caption_prefix: None
caption_suffix: None
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
is_reg: False
class_tokens: f1nni fox
caption_extension: .caption
[Subset 1 of Dataset 0]
image_dir: "F:\StableDiffusionProjects\LoRA\Character\Finni-v1.1-NAI\reg\1_fox"
image_count: 200
num_repeats: 1
shuffle_caption: True
keep_tokens: 0
caption_dropout_rate: 0.0
caption_dropout_every_n_epoches: 0
caption_tag_dropout_rate: 0.0
caption_prefix: None
caption_suffix: None
color_aug: False
flip_aug: False
face_crop_aug_range: None
random_crop: False
token_warmup_min: 1,
token_warmup_step: 0,
is_reg: True
class_tokens: fox
caption_extension: .caption
[Dataset 0]
loading image sizes.
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 182/182 [00:00<00:00, 5865.62it/s]
make buckets
min_bucket_reso and max_bucket_reso are ignored if bucket_no_upscale is set, because bucket reso is defined by image size automatically / bucket_no_upscaleが指定された場合は、bucketの解像度は画像サイズから自動計算されるため、min_bucket_resoとmax_bucket_resoは無視されます
number of images (including repeats) / 各bucketの画像枚数（繰り返し回数を含む）
bucket 0: resolution (320, 320), count: 1
bucket 1: resolution (448, 448), count: 5
bucket 2: resolution (512, 512), count: 319
bucket 3: resolution (576, 384), count: 25
mean ar error (without repeats): 0.0
preparing accelerator
loading model for process 0/1
load Diffusers pretrained models: runwayml/stable-diffusion-v1-5
text_encoder\model.safetensors not found
Loading pipeline components...: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:02<00:00, 2.26it/s]
You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
UNet2DConditionModel: 64, 8, 768, False, False
U-Net converted to original U-Net
Enable xformers for U-Net
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
import network module: networks.lora
[Dataset 0]
caching latents.
checking cache validity...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 182/182 [00:00<00:00, 181926.44it/s]
caching latents...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 182/182 [00:51<00:00, 3.52it/s]
create LoRA network. base dim (rank): 8, alpha: 1.0
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
create LoRA for Text Encoder:
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
prepare optimizer, data loader etc.
Traceback (most recent call last):
File "F:\StableDiffusionProjects\kohya_ss\library\train_util.py", line 3419, in get_optimizer
import bitsandbytes as bnb
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\__init__.py", line 6, in <module>
from . import cuda_setup, utils, research
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\research\__init__.py", line 1, in <module>
from . import nn
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\__init__.py", line 1, in <module>
from .modules import LinearFP8Mixed, LinearFP8Global
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in <module>
from bitsandbytes.optim import GlobalOptimManager
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\optim\__init__.py", line 6, in <module>
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py", line 5, in <module>
from .cuda_setup.main import evaluate_cuda_setup
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py", line 21, in <module>
from .paths import determine_cuda_runtime_lib_path
ModuleNotFoundError: No module named 'bitsandbytes.cuda_setup.paths'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "F:\StableDiffusionProjects\kohya_ss\train_network.py", line 1009, in <module>
trainer.train(args)
File "F:\StableDiffusionProjects\kohya_ss\train_network.py", line 338, in train
optimizer_name, optimizer_args, optimizer = train_util.get_optimizer(args, trainable_params)
File "F:\StableDiffusionProjects\kohya_ss\library\train_util.py", line 3421, in get_optimizer
raise ImportError("No bitsandbytes / bitsandbytesがインストールされていないようです")
ImportError: No bitsandbytes / bitsandbytesがインストールされていないようです
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "F:\StableDiffusionProjects\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main
args.func(args)
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command
simple_launcher(args)
File "F:\StableDiffusionProjects\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 628, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['F:\\StableDiffusionProjects\\kohya_ss\\venv\\Scripts\\python.exe', './train_network.py', '--enable_bucket', '--min_bucket_reso=256', '--max_bucket_reso=2048', '--pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5', '--train_data_dir=F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/img', '--reg_data_dir=F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/reg', '--resolution=512,512', '--output_dir=F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/model', '--logging_dir=F:/StableDiffusionProjects/LoRA/Character/Finni-v1.1-NAI/log', '--network_alpha=1', '--save_model_as=safetensors', '--network_module=networks.lora', '--network_dim=8', '--output_name=lora_Finni-v1.1-NoAI_SD15', '--lr_scheduler_num_cycles=12', '--no_half_vae', '--learning_rate=0.0001', '--lr_scheduler=constant', '--train_batch_size=1', '--max_train_steps=4200', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=58008', '--cache_latents', '--optimizer_type=AdamW8bit', '--max_token_length=150', '--clip_skip=2', '--bucket_reso_steps=64', '--shuffle_caption', '--xformers', '--bucket_no_upscale', '--noise_offset=0.0']' returned non-zero exit status 1.
Keyboard interruption in main thread... closing server.
Terminate batch job (Y/N)? y
(venv) F:\StableDiffusionProjects\kohya_ss>pip list
Package Version Editable project location
---------------------------- ------------ -----------------------------------
absl-py 2.0.0
accelerate 0.23.0
aiofiles 23.2.1
aiohttp 3.8.6
aiosignal 1.3.1
altair 4.2.2
annotated-types 0.6.0
anyio 3.7.1
appdirs 1.4.4
astunparse 1.6.3
async-timeout 4.0.3
attrs 23.1.0
bitsandbytes 0.41.1
cachetools 5.3.2
certifi 2022.12.7
charset-normalizer 2.1.1
click 8.1.7
colorama 0.4.6
coloredlogs 15.0.1
contourpy 1.2.0
cycler 0.12.1
dadaptation 3.1
diffusers 0.21.4
docker-pycreds 0.4.0
easygui 0.98.3
einops 0.6.0
entrypoints 0.4
exceptiongroup 1.1.3
fairscale 0.4.13
fastapi 0.104.1
ffmpy 0.3.1
filelock 3.9.0
flatbuffers 23.5.26
fonttools 4.44.0
frozenlist 1.4.0
fsspec 2023.10.0
ftfy 6.1.1
gast 0.5.4
gitdb 4.0.11
GitPython 3.1.40
google-auth 2.23.4
google-auth-oauthlib 1.0.0
google-pasta 0.2.0
gradio 3.36.1
gradio_client 0.7.0
grpcio 1.59.2
h11 0.14.0
h5py 3.10.0
httpcore 1.0.2
httpx 0.25.1
huggingface-hub 0.15.1
humanfriendly 10.0
idna 3.4
importlib-metadata 6.8.0
invisible-watermark 0.2.0
Jinja2 3.1.2
jsonschema 4.19.2
jsonschema-specifications 2023.7.1
keras 2.14.0
kiwisolver 1.4.5
libclang 16.0.6
library 1.0.3 F:\StableDiffusionProjects\kohya_ss
lightning-utilities 0.9.0
linkify-it-py 2.0.2
lion-pytorch 0.0.6
lycoris-lora 1.9.0
Markdown 3.5.1
markdown-it-py 2.2.0
MarkupSafe 2.1.3
matplotlib 3.8.1
mdit-py-plugins 0.3.3
mdurl 0.1.2
ml-dtypes 0.2.0
mpmath 1.3.0
multidict 6.0.4
networkx 3.0
numpy 1.24.1
oauthlib 3.2.2
onnx 1.14.1
onnxruntime-gpu 1.16.0
open-clip-torch 2.20.0
opencv-python 4.7.0.68
opt-einsum 3.3.0
orjson 3.9.10
packaging 23.2
pandas 2.1.3
pathtools 0.1.2
Pillow 9.3.0
pip 22.2.1
prodigyopt 1.0
protobuf 3.20.3
psutil 5.9.6
pyasn1 0.5.0
pyasn1-modules 0.3.0
pydantic 2.5.0
pydantic_core 2.14.1
pydub 0.25.1
Pygments 2.16.1
pyparsing 3.1.1
pyreadline3 3.4.1
python-dateutil 2.8.2
python-multipart 0.0.6
pytorch-lightning 1.9.0
pytz 2023.3.post1
PyWavelets 1.4.1
PyYAML 6.0.1
referencing 0.30.2
regex 2023.10.3
requests 2.28.1
requests-oauthlib 1.3.1
rich 13.4.1
rpds-py 0.12.0
rsa 4.9
safetensors 0.3.1
scipy 1.11.3
semantic-version 2.10.0
sentencepiece 0.1.99
sentry-sdk 1.35.0
setproctitle 1.3.3
setuptools 63.2.0
six 1.16.0
smmap 5.0.1
sniffio 1.3.0
starlette 0.27.0
sympy 1.12
tensorboard 2.14.1
tensorboard-data-server 0.7.2
tensorflow 2.14.0
tensorflow-estimator 2.14.0
tensorflow-intel 2.14.0
tensorflow-io-gcs-filesystem 0.31.0
termcolor 2.3.0
timm 0.6.12
tk 0.1.0
tokenizers 0.13.3
toml 0.10.2
toolz 0.12.0
torch 2.0.1+cu118
torchmetrics 1.2.0
torchvision 0.15.2+cu118
tqdm 4.66.1
transformers 4.30.2
typing_extensions 4.8.0
tzdata 2023.3
uc-micro-py 1.0.2
urllib3 1.26.13
uvicorn 0.24.0.post1
voluptuous 0.13.1
wandb 0.15.11
wcwidth 0.2.9
websockets 11.0.3
Werkzeug 3.0.1
wheel 0.41.3
wrapt 1.14.1
xformers 0.0.21
yarl 1.9.2
zipp 3.17.0
[notice] A new release of pip available: 22.2.1 -> 23.3.1
[notice] To update, run: python.exe -m pip install --upgrade pip
(venv) F:\StableDiffusionProjects\kohya_ss>
asbjbo
yeswecan
Fiendstar77
IvanDart1001
ZikViM
If I choose 8bit related：Traceback (most recent call last): File "E:\kohya_ss\library\train_util.py", line 3419, in get_optimizer import bitsandbytes as bnb File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes__init.py", line 6, in
from . import cuda_setup, utils, research
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\research__init__.py", line 1, in
from . import nn
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\ init.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\optim\ init__.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py", line 5, in
from .cuda_setup.main import evaluate_cuda_setup
File "E:\kohya_ss\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py", line 21, in
from .paths import determine_cuda_runtime_lib_path
ModuleNotFoundError: No module named 'bitsandbytes.cuda_setup.paths'
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "E:\kohya_ss\train_db.py", line 488, in
train(args)
File "E:\kohya_ss\traindb.py", line 171, in train
, _, optimizer = train_util.get_optimizer(args, trainable_params)
File "E:\kohya_ss\library\train_util.py", line 3421, in get_optimizer
raise ImportError("No bitsandbytes / bitsandbytesがインストールされていないようです")
ImportError: No bitsandbytes / bitsandbytesがインストールされていないようです
Traceback (most recent call last):
File "C:\Users\hjx43\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\hjx43\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "E:\kohya_ss\venv\Scripts\accelerate.exe__main__.py", line 7, in
File "E:\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 47, in main
args.func(args)
File "E:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 986, in launch_command
simple_launcher(args)
File "E:\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 628, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['E:\kohya_ss\venv\Scripts\python.exe', './train_db.py', '--enable_bucket', '--min_bucket_reso=256', '--max_bucket_reso=2048', '--no_token_padding', '--weighted_captions', '--pretrained_model_name_or_path=E:/sd-webui-aki/sd-webui-aki-v4.2/models/Stable-diffusion/ACertainThing-half.ckpt', '--train_data_dir=E:/xlzl/tupian/jpg', '--reg_data_dir=E:/DAIXUNLIAN1/reg', '--resolution=384,384', '--output_dir=E:/sd-webui-aki/sd-webui-aki-v4.2/models/Stable-diffusion', '--logging_dir=E:/kohya_ss/logs', '--stop_text_encoder_training=16673', '--save_model_as=safetensors', '--full_bf16', '--vae=E:/sd-webui-aki/sd-webui-aki-v4.2/models/VAE/vae-ft-mse-840000-ema-pruned.safetensors', '--output_name=shiyan', '--lr_scheduler_num_cycles=2', '--max_token_length=225', '--max_data_loader_n_workers=10', '--learning_rate=3e-06', '--lr_scheduler=constant_with_warmup', '--lr_warmup_steps=1667', '--train_batch_size=8', '--max_train_steps=33345', '--save_every_n_epochs=1', '--mixed_precision=bf16', '--save_precision=bf16', '--cache_latents', '--cache_latents_to_disk', '--optimizer_type=PagedAdamW8bit', '--lr_scheduler_args', 'Ir_end=1e-6', '--max_data_loader_n_workers=10', '--max_token_length=225', '--clip_skip=2', '--keep_tokens=3', '--caption_dropout_every_n_epochs=2', '--caption_dropout_rate=0.1', '--vae_batch_size=2', '--bucket_reso_steps=64', '--v_pred_like_loss=0.5', '--save_every_n_steps=2', '--save_last_n_steps=3', '--save_last_n_steps_state=1', '--min_snr_gamma=5', '--save_state', '--mem_eff_attn', '--flip_aug', '--gradient_checkpointing', '--xformers', '--persistent_data_loader_workers', '--bucket_no_upscale', '--noise_offset=0.11', '--adaptive_noise_scale=0.099']' returned non-zero exit status 1.
If I don't select 8bit related, I can start training then： Traceback (most recent call last): File "E:\kohya_ss\train_db.py", line 488, in
train(args)
File "E:\kohya_ss\train_db.py", line 279, in train
for step, batch in enumerate(train_dataloader):
File "E:\kohya_ss\venv\lib\site-packages\accelerate\data_loader.py", line 384, in iter
current_batch = next(dataloader_iter)
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data\dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data\dataloader.py", line 1371, in _process_data
data.reraise()
File "E:\kohya_ss\venv\lib\site-packages\torch_utils.py", line 644, in reraise
raise exception
AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\kohya_ss\venv\lib\site-packages\torch\utils\data\dataset.py", line 243, in getitem
return self.datasets[dataset_idx][sample_idx]
File "E:\kohya_ss\library\train_util.py", line 1201, in getitem
example["input_ids"] = self.tokenizer[0](captions, padding=True, truncation=True, return_tensors="pt").input_ids
AttributeError: 'DreamBoothDataset' object has no attribute 'tokenizer'